Zero-Shot Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 33
- 보존된 평가 기록
- 84
Zero-shot learning (ZSL) is a model's ability to detect classes never seen during training. The condition is that the classes are not known during supervised learning.
Earlier work in zero-shot learning use attributes in a two-step approach to infer unknown classes. In the computer vision context, more recent advances learn mappings from image feature space to semantic space. Other approaches learn non-linear multimodal embeddings. In the modern NLP context, language models can be evaluated on downstream tasks without fine tuning.
Benchmark datasets for zero-shot learning include aPY, AwA, and CUB, among others.
( Image credit: Prototypical Networks for Few shot Learning in PyTorch )
Further readings:
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Coordinated Cyber-Attack Detection Model of Cyber-Physical Power System Based on the Operating State Data Link
Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification
Zero-Shot Learning Based on Knowledge Sharing
Learning Transferable Visual Models From Natural Language Supervision
Knowledge-aware Zero-Shot Learning: Survey and Perspective
A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectives
Multi-Knowledge Fusion for New Feature Generation in Generalized Zero-Shot Learning
Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning
Wider Vision: Enriching Convolutional Neural Networks via Alignment to External Knowledge Bases
Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction
Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries
OntoZSL: Ontology-enhanced Zero-shot Learning
Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition
AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition
Robust Motion In-betweening
An Efficient Framework for Zero-Shot Sketch-Based Image Retrieval
End-to-end Generative Zero-shot Learning via Few-shot Learning
Adversarial Training of Variational Auto-encoders for Continual Zero-shot Learning(A-CZSL)
Zero-shot Learning with Deep Neural Networks for Object Recognition
Transductive Zero-Shot Learning by Decoupled Feature Generation
Video Action Recognition Using spatio-temporal optical flow video frames
Relaxed Transformer Decoders for Direct Action Proposal Generation
Learning Graph Embeddings for Compositional Zero-shot Learning
Isometric Propagation Network for Generalized Zero-shot Learning
GCF-Net: Gated Clip Fusion Network for Video Action Recognition
Cyber-Attack Detection in Discrete Nonlinear Multi-Agent Systems Using Neural Networks
Semantic Borrowing for Generalized Zero-Shot Learning
Open World Compositional Zero-Shot Learning
Stimuli-Sensitive Hawkes Processes for Personalized Student Procrastination Modeling
NTU-X: An Enhanced Large-scale Dataset for Improving Pose-based Recognition of Subtle Human Actions
Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition
Generative Multi-Label Zero-Shot Learning
SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models
Cross Knowledge-based Generative Zero-Shot Learning Approach with Taxonomy Regularization
Generative Replay-based Continual Zero-Shot Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.